FAI: FairGame: An Audit-Driven Game Theoretic Framework for Development and Certification of Fair AI

FAI：FairGame：用于公平人工智能开发和认证的审计驱动的博弈论框架

• 批准号: 1939677
• 负责人: Yevgeniy Vorobeychik
• 金额: $ 44.41万
• 依托单位: Washington University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-01-01 至 2023-12-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1939677&HistoricalAwards=false
• 关键词: FAI; FairGame; Audit; Driven; Game

The increasing impact of AI technologies on real applications has subjected these to unprecedented scrutiny. One of the major concerns is the extent to which these technologies reproduce or exacerbate inequity, with a number of high-profile examples, such as bias in recidivism prediction, illustrating the potential limitations of, and eroding trust in, AI. While approaches have emerged that aim to guarantee some form of fairness of AI systems, most are restricted to relatively simple prediction problems, without accounting for specific use cases of predictions. However, many practical uses of predictive models involve decisions that occur over time, and that are obtained by solving complex optimization problems. Moreover, few general approaches exist even for ascertaining equitable outcomes of dynamic decisions, let alone providing guidance for ensuring equity in such settings. To address these limitations, this project is developing a framework called FairGame for the development and certification of fair autonomous decision-making algorithms. This project will also develop new courses and course modules at Washington University, take a lead role in a new interdisciplinary program in Computational and Data Sciences, seek to inform policymakers and regulators about computational approaches to ensuring fairness, and work to broaden participation in computing through, for example, the Missouri Louis Stokes Alliance for Minority Participation.This project develops an audit-driven game theoretic framework for the development and certification of fair autonomous decision-making algorithms. FairGame features a decision module that computes a decision policy, and a pseudo-adversarial auditor providing feedback to the decision module about possible fairness violations, as well as providing fairness certification. The FairGame framework conceptually resembles the well-known actor-critic methods in reinforcement learning; however, unlike actor-critic methods, it enforces that the auditor has only query access to the policy, and, conversely, the decision module can only query the auditor (which provides feedback on the decisions). Different notions of fairness and efficacy can be modeled as different types of two-player games between the decision module and the auditor. This project will study foundational issues in this framework, including (a) the extent to which (probabilistically) certifying fairness in a black-box setting is possible, (b) practical algorithms for auditing, (c) iterative approaches for ensuring fair-decisions given a black-box access to an auditor, including policy gradient methods and Bayesian optimization, and (d) appropriate fairness and efficacy criteria, and (e) whether these criteria can satisfy different regulatory models, such as a requirement of “meaningful information about the logic” or legally imposed requirements of nondiscrimination. The work will be informed by the real policy challenge of developing fair algorithms for provision of services to homeless households, and provide feedback in this domain to key stakeholders.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

人工智能技术对真实的应用程序的影响越来越大，使这些应用程序受到前所未有的审查。 其中一个主要问题是这些技术在多大程度上再现或加剧了不平等，一些引人注目的例子，例如累犯预测的偏见，说明了人工智能的潜在局限性和对人工智能的信任。 虽然已经出现了旨在保证人工智能系统某种形式的公平性的方法，但大多数方法仅限于相对简单的预测问题，而没有考虑到预测的特定用例。 然而，预测模型的许多实际用途涉及随着时间的推移而发生的决策，并且通过解决复杂的优化问题来获得。 此外，即使是确定动态决策的公平结果的一般方法也很少，更不用说为确保这种情况下的公平提供指导了。为了解决这些限制，该项目正在开发一个名为FairGame的框架，用于开发和认证公平的自主决策算法。该项目还将在华盛顿大学开发新的课程和课程模块，在计算和数据科学的新跨学科项目中发挥主导作用，寻求向政策制定者和监管机构提供有关确保公平的计算方法的信息，并努力扩大对计算的参与，例如，密苏里州路易斯·斯托克斯少数民族参与联盟。该项目开发了一个由政府驱动的博弈论框架，用于开发和认证公平的自主决策-做算法 FairGame有一个计算决策策略的决策模块，以及一个伪对抗审计器，向决策模块提供有关可能违反公平性的反馈，并提供公平性认证。FairGame框架在概念上类似于强化学习中著名的actor-critic方法;然而，与actor-critic方法不同的是，它强制要求审计员只能查询策略，相反，决策模块只能查询审计员（提供决策反馈）。不同的公平性和有效性的概念可以被建模为不同类型的决策模块和审计员之间的两个玩家的游戏。 本项目将研究这一框架内的基本问题，包括（a）（概率上）证明黑箱设置中的公平性是可能的，（B）用于审计的实用算法，（c）用于确保审计员黑箱访问的公平决策的迭代方法，包括策略梯度方法和贝叶斯优化，以及（d）适当的公平性和有效性标准，以及（e）这些标准是否能够满足不同的监管模式，例如“关于逻辑的有意义信息”的要求或法律规定的非歧视要求。这项工作将通过制定为无家可归家庭提供服务的公平算法的真实的政策挑战来了解，并向关键利益相关者提供这一领域的反馈。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Manipulating Elections by Changing Voter Perceptions

通过改变选民的看法来操纵选举

• DOI: 10.24963/ijcai.2022/79
• 发表时间: 2022
• 期刊: International Joint Conference on Artificial Intelligence
• 作者: Wu, Junlin;Estornell, Andrew;Kong, Lecheng;Vorobeychik, Yevgeniy
• 通讯作者: Vorobeychik, Yevgeniy

Probabilistic Generating Circuits

• 发表时间: 2021-02
• 期刊: ArXiv
• 作者: Honghua Zhang;Brendan Juba;Guy Van den Broeck

Race-Aware Algorithms: Fairness, Nondiscrimination and Affirmative Action

种族感知算法：公平、非歧视和平权行动

• 发表时间: 2022
• 期刊: California law review
• 影响因子: 2.4
• 作者: Kim, Pauline T

The Many Faces of Adversarial Machine Learning

• DOI: 10.1609/aaai.v37i13.26796
• 发表时间: 2023-06
• 作者: Yevgeniy Vorobeychik

Learnability with PAC Semantics for Multi-agent Beliefs

多智能体信念的 PAC 语义的可学习性

• DOI: 10.1017/s1471068423000182
• 发表时间: 2023
• 期刊: Theory and Practice of Logic Programming
• 影响因子: 1.4
• 作者: MOCANU, IONELA G.;BELLE, VAISHAK;JUBA, BRENDAN
• 通讯作者: JUBA, BRENDAN